Skip to content
AI Atlas
Research

Papers

Publications linked to models, labs and benchmarks. Authors, venues and abstracts come from arXiv and publisher pages; model links come from model cards citing the paper.

341 papers

Papers
TitleAuthorsOrganizationPublishedIntroduces Models (and artifacts) whose model card or documentation cites this paper — inbound described_by relations.DatasetsBenchmarksCode
BiHDTrans: binary hyperdimensional transformer for efficient multivariate time series classificationarXiv:2509.24425cs.LGJingtao Zhang, Yi Liu, Qi Shen +111 Sept 2026
Autonomous-Flow-Based GenerationarXiv:2511.09902cs.LGHossein Rouhvarzi, Anastasis Kratsios11 Sept 2026
When do cheap embeddings beat protein language models? A theoretically-grounded hashing sketch for biological sequence classificationarXiv:2512.10147cs.LGSarwan Ali, Taslim Murad, Imdadullah Khan +111 Sept 2026
UBCL: A Reinforcement Learning Framework for Controllable and Diverse Player BehaviorsarXiv:2512.10835cs.LGAtahan Cilan, Atay \"Ozg\"ovde11 Sept 2026
Semidefinite Programming for Quantum Channel LearningarXiv:2601.12502cs.LGMikhail Gennadievich Belov, Victor Victorovich Dubov, Vadim Konstantinovich Ivanov +211 Sept 2026
Smoothing the Score Function to Enhance Generalization in Diffusion ModelsarXiv:2601.19285cs.LGXinyu Zhou, Jiawei Zhang, Stephen J. Wright11 Sept 2026
Prediction--Loss Alignment for Sampler--Robust Flow Matching TrainingarXiv:2602.10420cs.LGJiadong Hong, Lei Liu, Xinyu Bian +211 Sept 2026
Evaluating Memory Structure in LLM AgentsarXiv:2602.11243cs.LGAlina Shutova, Alexandra Olenina, Ivan Vinogradov +111 Sept 2026
Partial GFlowNet: Accelerating Convergence in Large State Spaces via Strategic PartitioningarXiv:2602.11498cs.LGXuan Yu, Xu Wang, Rui Zhu +211 Sept 2026
Measuring Progress in Reasoning Toward Mathematical Discovery with Automatic VerificationarXiv:2603.15617cs.LGErik Y. Wang, Sumeet R. Motwani, James V. Roggeveen +211 Sept 2026
Longitudinal Risk Prediction in Mammography with Privileged History DistillationarXiv:2603.15814cs.LGBanafsheh Karimian, Soufiane Belharbi, Alexis Guichemerre +211 Sept 2026
FluxMoE: Decoupling Expert Residency for High-Performance MoE ServingarXiv:2604.02715cs.LGQingxiu Liu, Yongchao He, Runhan Jiang +211 Sept 2026
Generalization Guarantees on Data-Driven Tuning of Gradient Descent with Langevin UpdatesarXiv:2604.13130cs.LGSaumya Goyal, Rohith Rongali, Ritabrata Ray +111 Sept 2026
DP-Muon: Differentially Private Optimization via Matrix-Orthogonalized MomentumarXiv:2605.12994cs.LGJihwan Kim, Chenglin Fan11 Sept 2026
Assessing Predictive Models for Fairness Based on Activity-Space PatternsarXiv:2605.23234cs.LGFrancesco Lettich, Mario A. Nascimento, Chiara Pugliese +111 Sept 2026
Benchmarking non-conformity score functions in conformal predictionarXiv:2605.24983cs.LGSol Erika Boman11 Sept 2026
Using Seismic Statistical Features and VQ-VAE to Improve Spatiotemporal Seismicity PredictabilityarXiv:2606.10069cs.LGWei Quan, Denise Gorse11 Sept 2026
Attention by Synchronization in Coupled Oscillator NetworksarXiv:2606.12059cs.LGFabio Pasqualetti, Taosha Guo11 Sept 2026
SafeImpute: Reliable Clinical Data Imputation via Conformal SelectionarXiv:2607.05613cs.LGXinrui He, Mengting Ai, Junting Wang +211 Sept 2026
RDQ: Residual Distribution Quantization for Large Language ModelsarXiv:2607.10137cs.LGPrateek Singh11 Sept 2026
Progressive Agent Skill Generation via Reinforcement LearningarXiv:2608.01678cs.LGJunhao Shen, Zhanqiu Zhang, Yiwen Guo +111 Sept 2026
Scaling Automatic Research Agents via World ModelsarXiv:2608.12564cs.LGXiyuan Yang, Sheikh Sarwar, Jingru Cheng +211 Sept 2026
Transfer Learning of Keystroke Dynamics for Cross-Device User AuthenticationarXiv:2608.16334cs.LGNuwan Kaluarachchi, Sevvandi Kandanaarachchi, Kristen Moore +211 Sept 2026
Designing a Robust LLM-Based Evaluation System for Agentic AI in Drug Discovery Through Human AlignmentarXiv:2608.21057cs.LGEmma Granqvist, Roc\'io Mercado, Samuel Genheden11 Sept 2026
Toward a First-Principles Update Geometry for the Language-Model HeadarXiv:2608.22253cs.LGAditya Somasundaram, Charles Guille-Escuret, Alexander Moreno +211 Sept 2026

Author lists and categories are copied from the paper's own metadata (arXiv, publisher). Linked models, datasets, benchmarks and code come from stated relations only; a dash means no source stated one.